Research map / Image generation / Image restoration
Multispectral Images Denoising by Intrinsic Tensor Sparsity Regularization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ITS regularization combining Tucker core sparsity and mode-wise low-rank terms | MSI denoising · Columbia MSI Database, simulated denoising | PSNR: 36.18±3.03 -> 37.78±3.32 | Helped |
| Use ITS regularization combining Tucker core sparsity and mode-wise low-rank terms | MSI denoising · Columbia MSI Database, simulated denoising | SSIM: 0.87±0.07 -> 0.90±0.07 | Helped |
| Use ITS regularization combining Tucker core sparsity and mode-wise low-rank terms | MSI denoising · Columbia MSI Database, simulated denoising | FSIM: 0.94±0.03 -> 0.96±0.02 | Helped |
| Use ITS regularization combining Tucker core sparsity and mode-wise low-rank terms | MSI denoising · Columbia MSI Database, simulated denoising | ERGAS: 91.20±29.70 -> 77.35±30.16 | Helped |
| Remove the Tucker-core sparsity term from ITS (ablation) | ITSReg · Face MSI from Columbia Dataset, different noise levels | PSNR | Hurt |
| Remove the mode-wise rank-product term from ITS (ablation) | ITSReg · Face MSI from Columbia Dataset, different noise levels | PSNR | Hurt |
| Remove the Tucker-core sparsity term from ITS (ablation) | ITSReg · Face MSI from Columbia Dataset, different noise levels | SSIM | Hurt |
| Remove the mode-wise rank-product term from ITS (ablation) | ITSReg · Face MSI from Columbia Dataset, different noise levels | SSIM | Hurt |
Closest papers by meaning
- Hyper-Laplacian Regularized Unidirectional Low-Rank Tensor Recovery for Multispectral Image Denoising (CVPR 2017 · similarity 0.92)
- Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising (CVPR 2019 · similarity 0.90)
- Tensor Compressive Sensing Fused Low-Rankness and Local-Smoothness (AAAI 2023 · similarity 0.88)
- Refining Dual Spectral Sparsity in Transformed Tensor Singular Values (ICML 2026 · similarity 0.87)
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.87)
- HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.